OJBench: leaderboard
Competitive-programming benchmark drawn from NOI and ICPC-style online-judge tasks, evaluating algorithm design and code correctness.
Metric: Score (%). Source: arxiv.org. Source: llm-stats.com. Saturation forecast: Estimated already saturated. 9 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Kimi K2.6 | 60.6 | #104 |
| 2 | Qwen 3.5 27B | 40.1 | #187 |
| 3 | Qwen 3.5 122B A10B | 39.5 | #173 |
| 4 | Qwen 3.5 35B A3B | 36 | #256 |
| 5 | Qwen 3 235B A22B 2507 (Thinking) | 32.5 | #260 (Qwen 3 235B A22B 2507) |
| 6 | Qwen 3 Next 80B A3B (Thinking) | 29.7 | #320 (Qwen 3 Next 80B A3B) |
| 7 | Kimi K2 | 27.1 | #243 |
| 8 | Kimi K2 0905 | 27.1 | #288 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=ojbench · How It Works · Data refreshed daily, snapshot 2026-10-20.